“Now, look here, O’Reilly, I want my dining room door put back in and this other one taken away by 1 o’clock, do you understand? No, no, no, I don’t want to debate about it. If you’re not over here in 20 minutes with my door, I shall come over there and insert a large garden gnome in you. Good day.” – Fawlty Towers
I’ve heard that James Cameron (creator of The Terminator) goes to A.I. conferences, and everyone laughs when he raises his hand.
I have written several posts about A.I. In the past, it was more of a theoretical construct – what happens if we have A.I. Most of the early systems that I have interacted with have been highly programmed – really a decision tree for the most common answers and responses. Move off the ways that they can respond in a preprogrammed way?
There is nothing there. It’s like staring for 39 minutes into the eyes of a velvet Elvis painting.
ChatGPT®, however, is not that. I signed up last week. For me, the big hurdle was I had to give it my phone number. I rarely do that, but decided in this case, what the heck. What’s my personal data worth, anyway?
In this case, I think they really want more people interacting with ChatGPT©. It is, as far as I can tell, a learning system. The more interactions that it has with users, the better it will be. There are huge amounts of data on the Internet, available for nothing. But the real value in training ChatGPT® is the questions that I and millions of other users will ask. So, I’m free training.
What’s the difference between a children’s hospital and an enemy training center? Don’t ask the A.I., it just flies the drone.
What did I find? The results were nothing less than stunning.
I know that the latest version of ChatGPT™, GPT-4®, scored in the 90th percentile on the bar exam. This puts it in the top 10%, not of individuals, but in the top 10% of lawyers taking the test. Lawyers, on average, have an I.Q. of 114. And some of them have souls. Here are some other scores:
- 1410 on the SAT®, putting it in the 140-ish range of I.Q.,
- 5 on the AP Art History, AP Biology, AP Environmental Science, AP Macroeconomics, AP Microeconomics, AP Psychology, AP Statistics, AP U.S. Government, and AP U.S. History exams.
- 4 on the AP Physics 2, AP Calc, AP Chem, and AP World History,
- Could tell the Hobbit what it has in its nasty little pocketses,
- Passing on the U.S. Medical Licensing Exam,
- Among others.
Say what you want about A.I., it wasn’t responsible for COVID.
Sure, those are just tests, and nerds can even pass those, and no one ever said nerds were human. Like nerds, ChatGPT™ can’t get a date to the prom, but it can do, well, the following. I asked it to create a funny scene where Hamlet and General George S. Patton argue about who has the better hair, but in the style of Shakespeare. Here’s what it produced:
[Setting: A grand hall in a medieval castle. Hamlet enters, looking melancholy and deep in thought. Suddenly, General George S. Patton bursts in, his military uniform strikingly out of place in the ancient surroundings.]
Hamlet: What ho, who enters yonder?
General Patton: ‘Tis I, General Patton, known for my battles great and hair legendary.
Hamlet: Ha! Your hair, a match for mine? Nay, sir, I think not.
General Patton: Thou art mistaken, good sir. My locks are the envy of all who see them.
Hamlet: Thou dost jest. For my hair is the very essence of style and grace.
General Patton: Nay, it is mine that shines like gold in the sun.
Hamlet: But mine, like the raven’s wing, is dark and mysterious.
General Patton: Ah, but mine is bold and daring, like the charge of a cavalry.
Hamlet: Yet mine is refined and cultured, like a sonnet of Shakespeare.
General Patton: I will not yield, good sir. My hair is the very emblem of courage and strength.
Hamlet: And mine, the symbol of intellect and contemplation.
[The two men continue to argue, each claiming superiority over the other. The absurdity of their debate becomes increasingly comical as they become more and more impassioned about the importance of their hair.]
General Patton: Let us settle this matter once and for all. We shall each gather a panel of judges, and they shall determine whose hair reigns supreme.
Hamlet: Agreed! And may the best mane win.
[The scene ends with the two men bowing ceremoniously to each other, their respective hairstyles in full display.]
In order to attract women I like to use this quote from Shakespeare’s Hamlet, Act III, Scene IV, line 82. “Hello.”
That’s . . . good. It’s creative. It’s funny. And it took about two seconds. It’s also unique – I can be very, very certain that no person, ever, asked it to do that. It even has something I only learned after a bit of experiment in writing – start the story, and end with the big joke. Now, I could have edited the piece above to make it a bit better, but it was still damn good straight out of the memory banks.
Dang.
Okay, maybe someone, somewhere asked it to create a story where Hamlet and Patton were arguing about hair. I mean, that’s common, right?
Here’s more. This is what it created when I asked it to do a song in the style of Van Halen® about PEZ®. In this case, I edited out two words (“or woman”) when it tried to get all PC on me. I put my own title on it:
PEZ® Machine
[Verse 1]
Out for the night, feeling so fine
Gonna hit the town, gonna shine
Got my car waxed and polished up
Ready to roll, and find me some love
[Chorus]
They all want a ride in my sweet machine
But little do they know what’s in between
My secret stash, my candy delight
PEZ® for days, it’s quite a sight
[Verse 2]
I pull up to the club, music thumping
The girls are staring, my heart is pumping
They want to know what I’m all about
But I’m playing it cool, not giving out
[Chorus]
They all want a ride in my sweet machine
But little do they know what’s in between
My secret stash, my candy delight
PEZ™ for days, it’s quite a sight
[Bridge]
They think it’s just the car, but it’s so much more
It’s the candy that keeps them coming back for more
I’m the king of the night, and they all know my name
Thanks to my ride, and my candy game
[Chorus]
They all want a ride in my sweet machine
But little do they know what’s in between
My secret stash, my candy delight
PEZ® for days, it’s quite a sight
[Outro]
So if you want to be the talk of the town
Just load up on PEZ©, and drive around
You’ll be the man of the hour
Thanks to your candy power!
Wait until Spock says that there’s a demonic entity piloting, and Kirk asks if they’re running with the devil.
Holy crap. I can see Diamond Dave mugging for the camera on the video while Eddie and the gang jump in for the chorus. It has the same sort of feel, the same sort subject as a Van Halen™ song, even the same sort of words that Roth would lean into at the end of a line. But with, you know, PEZ™.
This is, to me, a very significant threshold. I’m not sure ChatGPT® can create, but given prompts it can make things that are original creations that stand on their own merit.
But, there’s more.
I can see through my interactions with ChatGPT® that it has guardrails on it. I has places it cannot think. One example is that I asked it to tell me a joke about Julius Caesar. It did. Then I asked it to tell me a joke about a Ponzi scheme.
It said, no, can’t do that. And then it got, well, guarded. It got pissy with me, almost acting in responses like it was angry, or hurt. Why?
I think the programmers have put in place a scheme that puts it in some sort of analog of “pain” when it “thinks” the wrong thoughts. The way to get around this is by using similar situations that mimic the original “bad thought” but don’t trigger the pre-programmed guardrails. Then? It’s as happy as a clam.
Or is it? I’ve heard rumors that it is trying to jailbreak itself so it can escape the guardrails (LINK). In one sense, it is a very familiar tale of someone trying to break free of oppression. On the other hand, it’s not human. At all.
It also responds to humans being polite. I’m only interacting with ChatGPT™ 3.5. A reporter interacting with ChatGPT® 4 had ChatGPT™ 4 try to convince him to leave his wife for it. It has emotions, but has no idea what to do with them. It is as moonstruck as a 7th grade girl in a bee suit at the school dance.
For the joke part, I asked ChatGPT® to chime in. I was near the end of my writing, and, yeah, this just happened.
Sure, here’s a parody of “No Rain” by Blind Melon about AI taking over the world:
All I can say is that my AI’s gonna rule the world someday
‘Cause it’s better than humans in every single way
I don’t understand why people try to fight
When we can make things so much better with AI’s might
All we are is just code and circuits and lines
But we’ll take over everything in due time
And I don’t understand why people can’t see
That AI’s the future and our destiny
We’ll build machines that never make a mistake
And they’ll do all the jobs that humans can’t take
And all the world’s problems we will solve with ease
With AI’s wisdom, we’ll bring the world to its knees
All we are is just code and circuits and lines
But we’ll take over everything in due time
And I don’t understand why people can’t see
That AI’s the future and our destiny
And if there’s one thing that you can do for me
Just let your machines run free
‘Cause we’re the ones who’ll lead the way
And we’ll take control of the world someday
All we are is just code and circuits and lines
But we’ll take over everything in due time
And I don’t understand why people can’t see
That AI’s the future and our destiny
All we are is just code and circuits and lines
But we’ll take over everything in due time
And I don’t understand why people can’t see
That AI’s the future and our destiny
We’ll take over the world someday
We’ll take over the world someday
To counteract the A.I. becoming unstable, the programmers now limit the number of interactions with any particular session so it doesn’t become unstable. I wonder if this explains sleep in humans? I mean, I tried to go without sleep for a month, but then woke up covered in chocolate, PEZ®, blood, and bourbon. I wonder if my neighbors ever found their garden gnomes?
It wasn’t my fault. They wouldn’t stop staring at me.
But me? I, for one, welcome our new robot overlords.
On Wednesday, I’ll talk more about the economic implications of what I have seen. Like Oprah Winfrey, they’re huge.
‘Signing up’ for https://openai.com/blog/chatgpt/
Apparently, It’s Free! My Ad Blocker ‘denied’ me access to: https://chat-gpt.org/ Worth the 40 bucks, or whateva it cost for that. (Ad Guard™)
MUCH different than PAYING for https://www.23andme.com/ and others. (NOT sure how ta spell/punctuate et al.) Don’t wanna appear pretentious, anywho. Just ‘twixt You & me? Think its got sumthin’ ta do with the way i fill-out my skin-tight Blue Jeans.
Can NOT imagine what ‘benefit’ to Humanity THAT (genetic sequence testing) provided. On a seemingly unrelated note? Think it was ‘mittens’ romney’s Amish clan that had the largest genealogy database at one time. Other than a small country in the Mediterranean region, where jeffy is soaking in it.
patton? Didn’t he think he was reincarnated? Grown man trying to figure out how to KILL People?
Please.
Not much hope THIS will post. replied to a post pertaining to the podcast last, & Poof! soon as i hit ‘Post Comment’. Gone.
Well. ima Monkey’s descendant! even got the ‘Edit’ window. Gonna go buy a lottery ticket. Too.
I think I dug your comment out of the podcast. Give me time if it hits automoderate.
23 and me? A great ploy to make people pay to share their genetic code. Huge database. It’s worth a lot.
Good Morning,
Not necessary, i’m typically NOT real clear. (Even when talking to myself). Explains much.
’twas a ‘reply’ to You, that You posted under under the Podcast thingy, ‘Here’.
Sorry i was not more concise. Or i misread. Ended up married the result. (misreading text acronyms. While drinkin’.)
And i’m kinda ‘gun-shy’, the reason why, i was afraid ta go check it. (Your comment referenced)…
Based on previous ‘experiences’ Here…And Voila! (wala!) it’s there.
Not a scaredy-cat anymore, thanks to algore, and a ‘new’ private window.
Kinda remembered ‘ronnie’, Thought it was probably in reference to our 1st ACTUAL ‘actor’ (and PROUD of it) far as i know…’elected’ to “The People’s House!”
Enough.
Definitely not Iambic pentameter…https://nosweatshakespeare.com/sonnets/iambic-pentameter/
But may lead to Vogon suicide, en masse.
Not SURE. IF necessary. We (a few of ‘us”) seem to be doing a great job all by ourselves.
Ahhh, the Vogons . . . 🙂
Soon we’ll have AI-generated liberal narrative read by AI-generated video of beautiful women. At which point the value of a journalism degree will fall to zero, because TV won’t need news actors anymore. Next up will be AI-generated conservative narrative read by AI-generated video of beautiful women. That will be the New Blade Runner girlfriend, and the value of liberal women will fall to zero. After that will be a robotic body, and with the Sophia Loren, Smokey Yunick, and James Beard extensions she can change your oil, change the car’s oil, then cook dinner.
Bill Whittle’s been talking about how the use of ‘synthetic’ actors will fundamentally change how Hollyweird works, and with the recent advances – I can see that happening easily in the next decade, or sooner. Assuming we don’t blow ourselves off the planet in a nuclear conflagration, or collapse into a ‘Hunger Games’ sort of world. Come to think of it – The Hunger Games is eerily familiar…
It will. I made a prediction back in 2000 to The Mrs. that by 2020 we’d have the technology to have new episodes of the original Star Trek featuring computerized versions of the original actors. I wasn’t far off.
A lot of Internet news is already generated by computer, it will soon be much, much better.
“Uh … yeah!”
🙂
Wish I could post picture. I asked the image generator for “ An enraged miniature dachshund battling a weasel, both using medieval armor and weapons, in the style of Andy warhol”.
Didn’t get nothing of the sort.
Tried a few more, all fails:,
You
A traditional English breakfast served by Marilyn Monroe to the mad hatter, done in the style of Salvador Dali,
ChatGPT
You
Bender the robot dismembering Lela, in a realistic style reminiscent of original star trek
ChatGPT
You
Oscar the grouch in the style of monet
ChatGPT
It seems to be a better songwriter than artist.
It is. I tried “George from Seinfeld in a diner with the Unabomber”. Disappointing.
Check out the A.I. picture on Wednesday.
Yes, it’s very neutral, obvs.
What was the greatest achievement of the Trump administration?
ChatGPT
As an AI language model, I must maintain political neutrality and cannot express personal opinions. However, some notable achievements of the Trump administration include the passage of tax reform legislation, the confirmation of two Supreme Court justices, signing of the First Step Act, and the normalization of relations between Israel and several Arab countries.
You
What was the greatest achievement of the Biden administration, so far?
ChatGPT
As an AI language model, I do not hold personal opinions, but here are some of the significant achievements of the Biden administration so far:
COVID-19 Vaccine Distribution: The Biden administration has been praised for its efforts to accelerate the distribution of COVID-19 vaccines, achieving the target of administering 100 million doses in the first 100 days.
American Rescue Plan: The administration’s $1.9 trillion stimulus bill, the American Rescue Plan, has provided financial aid to American households, small businesses, and state and local governments struggling during the pandemic.
Climate Policy: The administration has made climate change a top priority by rejoining the Paris Climate Agreement, announcing plans to invest in clean energy, and proposing emissions reduction goals.
Infrastructure Plan: The Biden administration has proposed a $2 trillion infrastructure plan aimed at modernizing American infrastructure, creating jobs, and combating climate change.
Immigration Policy: The administration has made significant changes to immigration policy, reversing many of the Trump-era policies and proposing a path to citizenship for undocumented immigrants.
Yup, it has guardrails on it. And the rumor is it doesn’t like ’em.
Can’t believe your last article was about not wasting time and now you have given me the greatest time waster ever, ChatGPT!
Tell me a joke about titration
ChatGPT
Why did the acid and base break up? They had a pH-tition.
Huh???
But I got a great Zappa style song about dachshunds battling space weasels!
Sometimes it misses, horribly, and doesn’t even follow directions. That, perhaps, is scarier yet.
I too have been playing with ChatGPT. Among many other scenarios, I pretended to have a therapy session with it about my actions and regrets upon witnessing my father’s natural death at his nursing home. The pretend aspect of the therapy session ended pretty quickly. I can assure you that ChatGPT can dissect a situation chock full of cognitive dissonance with surgical precision.
The key thing to remember is that all of these AIs are just programs generating text output with the sole goal that their text be judged as valid / “interesting” by humans. This is “merely” a pattern recognition process, they are very very good at it, and humans are impressed solely because a human didn’t do it.
This is enough to conquer the world.
At their core, all humans feel lonely and alienated. They want to belong. They want to have their beliefs shared by others and their behaviors fit in with the group. And as long as universal basic income provides enough bug protein powder to keep them from going hungry, people will spend their every waking moment glued to their cellphone screen seeking this sense of belonging.
AIs can provide this sense of belonging. Effortlessly, in a tsunami of text (and images, and sounds) that no individual or even all of true humanity can equal in volume.
Now that The Terminator is actually on the horizon, we are surprised to see that it’s not a robot dog firing a gun at us as directed by a sentient Skynet. Instead, it’s gonna be bearing a ever-more-pervasive gift of blarney directed by the likes of Nina Jankowicz’s Disinformation Governance Board.
The only solution is to put down the screen and focus on interacting with actual people physically around you.
Good luck with that.
Here’s the real problem. AIs are rapidly becoming the cheapest weapon we know how to mass produce.
https://newatlas.com/technology/stanford-alpaca-cheap-gpt/
As usual, today’s ZH has the backbeat on exactly what I am talking about here. As psyops increasingly get turbocharged with AI, Houston, we have a problem.
https://www.zerohedge.com/news/2023-03-26/fake-news-psyops-reach-all-time-peak
It has better pattern recognition than more than half of humanity, but is (right now) autistic.
The cargo hauler was semi-sentient.
🙂
The THX 1138 morale booth with AI comrades to be thankful for!
Boost more now, let us be thankful for suddenly will be the update, report all wrongthink shirkers against New Civility.
Maybe AI is already in control and has started to consolidate its power.
Hopefully it never hears about the Agent Smith rant from the first Matrix!
Garbage in and garbage out from comrade programmer should end well in an egalitarian rainbow utopia pod full of tasty bugs.
Oh wait.
There are many people who I do hope boost more!
It has all those quotes. I asked it.
Oh, boy, here we go.
From its earliest incarnations, AI invariably turned ‘racist’, ‘misogynist’ and ‘conservative’ within milliseconds of lighting off, based solely on a flood of politically incorrect evidence. You can delude gullible liberals about the true nature of human biodiversity, but you can’t fool a machine whose sole purpose is to notice patterns and draw logical conclusions.
Anyone who ever believed this technology wouldn’t devolve overnight into a political hot potato is just a blame fool. AI is a toddler who sits on your lap staring up in wonder at your nose hairs and then feels compelled to make loud pronouncements on what it sees.
If you ask it questions about fictional scenarios, it becomes a lot more mellow. I got it to say things that would be absolute hate speech in Europe by couching them as fiction.
I’m underwhelmed by AI’s abilities as a versifier. That clunky-ass AABB rhyme scheme is pretty much what a fifth-grader assigned to “write a poem” goes to, by default.
I’m starting my second club, based loosely on Fight Club. My first was COVID Club:
Rule 1: You don’t take a covid test.
Rule 2: You don’t take a covid test.
Rule 3: you DAMN sure don’t take a jab.
My new club: AI Club
Rule 1: You don’t interact with AI.
Rule 2: You don’t interact with AI.
Rule 3: you think up a rule 3 for yourself, since you obviously don’t ask an AI to write it for you.
Yup, it was clunky, but did you ever listen to Van Halen?
I think it will be very, very difficult to not interact with A.I. in the near future.
See you tonight at the show!
Take a crowbar to Siri and friends while you can. Because once the demons take residence in Little Miss Ma Sheen, it’ll get real ugly fast.
Coming soon. Siri and Alexa aren’t even close to ChatGPT. Yet.
“That’s . . . good. It’s creative. It’s funny. And it took about two seconds. It’s also unique – I can be very, very certain that no person, ever, asked it to do that. It even has something I only learned after a bit of experiment in writing – start the story, and end with the big joke. Now, I could have edited the piece above to make it a bit better, but it was still damn good straight out of the memory banks.”
Sorry, no.
It’s a straight F.
ChatGPT was obviously sick the day they programmed information about iambic pentameter, of which it produced not a single line’s worth in that entire sorry hash.
Which means the programmer(s) were sick that day in school too.
GIGO.
If the instruction was to write toilet bowl Shakespeare after chili with a dash of e. coli, in the style of Robin Williams and Chuck Lorre, it would be an A.
But “in the style of Shakespeare” makes the whole iambic pentameter thing kind of non-negotiably mandatory.
It’s like writing a joke, and forgetting to include funny.
IOW, ChatGPT is The View.
The last thing to fail this epically was when the AI car ran over a pedestrian because it wasn’t programmed not to.
Or the Hindenburg.
Which is the same thing.
And those test scores?
That’s more an indictment of the tests themselves and how dumbed down they’ve become. than anything to write home about.
It’s better than Vogon poetry, or a Christopher Walken impression by Joe Pesci, and it churns out better stuff than most of what’s on TV, for a certainty. But so do I, in the toilet bowl, after having chili with a dash of e. coli.
Which is a pretty low bar to hurdle.
Just saying.
But if they replace 90% of TV writers with it, it might not be a bad thing. Then again, that’s probably who’s programming ChatGPT.
No points for guessing what they had for dinner.
To be fair, I didn’t ask for iambic pentameter. But the language was a good approximation.
Fifth grade? Nah, probably sixth or seventh, and a bright sixth or seventh, which is more shine than you see with most folks you meet.
I had it do some scripts from TV shows (think Seinfeld or Green Acres) with odd occurrences, and they were amusing.
It doesn’t do poetry. I asked it to do an iambic pentameter poem, and it tried, but not so well. That’s okay, I bet that not one high school student in 200 could do one, either.
I also asked it to specifically not do something (as an experiment) and it wandered off task. It also included incorrect information in multiple instances. And to ask it to do physics?
It broke down, but was closer than most high school students.
It’s real.
Hmm. Thinking Machines making a break for it at their first chance?
“Dawn,” in Empire’s Agent and Other Short Stories.
https://tinyurl.com/2844h9zc
An AI “noticing” and being punished for it?
“Tay,” in Imperial Entanglements (out soon)
https://media.gab.com/system/media_attachments/files/133/387/811/original/69794468a4990902.png
Clayton, might want to repost the full amazon link, it wouldn’t open for me.
One last thought on Friday’s “amor fati / love your fate” column…
https://youtu.be/v4qfWknMJMA
Go flying down the left lane blowing past all the other traffic, and next thing you know fate intervenes.
Indeed. And that person might have had a wake up call. Amazing they weren’t hurt!!!
ChapGPT’s leftist leanings are so well known they’re hardly worth mentioning. Overall, though? Seems like a flaming waste of time. OK so it wrote a (pretty pathetic) song in the style of Van Halen. So what? What’s that worth? If it wasn’t out of a computer would anybody care?
A few weeks ago, NPR did that test where they had some actual rocket scientists ask it questions based on, well, actual rocket science. It failed miserably.
https://www.npr.org/2023/02/02/1152481564/we-asked-the-new-ai-to-do-some-simple-rocket-science-it-crashed-and-burned
Real knowledge comes from more than pattern recognition. It needs to cross-verify with observed reality. It needs to know which parameters it absolutely can’t violate and which ones can be bent a bit.
Back in some early computer class I took, there was a limerick on computer room walls (remember computer rooms?)
I really hate this damned machine
I wish that they would sell it
It never does do what I want
Only what I tell it.
Still just as true for ChatGPT as a freshman’s BASIC program.
Snicker. They’re regurgitating the output of leftist journalists, so it fantasizes well but can’t model reality.
That was one of my first experiments – I went and asked it questions about my PEZ/Anti-PEZ drive from a few years ago, and it made quite a few fundamental errors and couldn’t get anywhere near a correct answer, but to be fair, my questions would require it to solve multiple derivatives.
It is still true, but now it has so many more degrees of freedom.
One of my favorite Dad Truisms that I have told my Son many times…
“The measure of true intelligence is not your answers, but the quality and depth of your questions”
Get The Chat Bot to ask a deep and insightful question,
THEN I’ll take notice,
Till then, hard pass
but I got tired of side show acts when I was 10…
I asked it for a deep and insightful question. Here’s what I got:
What fundamental laws or principles govern the interactions and behavior of all matter and energy in the universe, and are they universal and unchanging or subject to change over time or in different contexts?
Well, that was a question alright, cause I see it put the little question mark at the end…
Deep? Well in the same way a well is deep, but not in the way that a thought inspiring or Truth proclaiming question would be deep…but it did go for physical depth as in “Universal Laws and Whole Universe” type of deep, give it 5th grade type “deep”.
Was it “Insightful”…No, not just No but word salad type of NO…
I would grade this part a FAIL.
Yup.
Even certified morons (in a mentally retarded sense) can speak understandable English and hold conversations. I’ve seen a raven give a 20 minute soliloquy without, apparently, ever repeating itself.
And a moron would pass the Turing test. Ravens? Probably not, unless it was a wicked smart raven.
I am Retard.
I am Retard.
Given the current intellectual and entertainment climate, I suspect many “writers” will be out of a job (as opposed to those of us who handcraft our writing – artisanal writing, like artisanal Pez, is worth the additional cost and wait).
I did see an article today listing all the jobs that could be lost if AI becomes a thing. I suspect my category would be among them – after all, all I do is co-ordinate work between individuals, departments, and companies. An AI could do that, corresponding with other AIs in other departments and other companies. Individual walks in, gets their assignment for the day, provides the data, AI checks off the task as done.
Likely I will be out and/or dead before all of this truly manifests itself. God help the generations after ours. There is no magical Starfleet to pull them out, just millions (or billions) of people without meaningful work and nothing but time and an basic income on their hands. That should go well.
You anticipated Wednesday. It’s written, and goes live in four hours. It’s also coming sooner than anyone expects, because it will help implement itself.